Prediction of surface roughness in milling compacted graphite iron with artificial neural network and regression analysis
Yazarlar (3)
Şener Karabulut
Türkiye
Türkiye
Prof. Dr. Murat SARIKAYA Sinop Üniversitesi, Türkiye
Öğr. Gör. Abdulkadir Güllü Gazi Üniversitesi, Türkiye
| Bildiri Türü | Tebliğ/Bildiri | Bildiri Dili | İngilizce |
| Bildiri Alt Türü | Tam Metin Olarak Yayınlanan Tebliğ (Uluslararası Kongre/Sempozyum) | ||
| Bildiri Niteliği | Alanında Hakemli Uluslararası Kongre/Sempozyum | ||
| Kongre Adı | 2rd International Conference on Engineering and Natural Sciences (ICENS 2016) | ||
| Kongre Tarihi | 24-05-2016 / 28-05-2016 | ||
| Basıldığı Ülke | Bosna Hersek | Basıldığı Şehir | Saraybosna |
| Bildiri Linki | https://www.icens.eu/sites/default/files/2016/Chapter_1_checked_ABD_updated.pdf | ||
| UAK Araştırma Alanları |
Üretim Teknolojileri
|
||
| Özet |
| In the present study, it was investigated machinability of compacted graphite iron by using various lead angles and chip thickness and cutting speeds. Analytical models were developed for the prediction of surface roughness (Ra) values after face milling process. Experimental results have been modeled by using artificial neural networks and variance (ANOVA) analysis results and developed a prediction model. A comparison of ANN model with regression model is also carried out. Variance analysis results showed that a strong correlation between the lead angle, chip thickness and surface quality. The surface roughness values were improved while increasing the lead angle value from 45 to 88 in dry and wet milling of compacted graphite iron. The experimental results showed surface quality was improved between 3.0%-38% at the all lead angles when cutting oil was used in the experiments. |
| Anahtar Kelimeler |
